If you’ve been programming, or learning programming over the past year or so, you should have seen many of the coding assistants… MS Copilot, Claude, Chatgpt and similar. While these have been very handy in looking up how to build a thing – and even building the thing (sometimes successfully!) There are a lot of reasons why you should do the real coding for your project… Or at least read and add your changes and files manually, from a browser vs built in IDE features.
Continue reading “A Case Against the AI-IDE”ChatGPT reworking from overtly Sycophant answers
A recent news article across the internet the last day or so has been around the topic of excessively sycophant answers, or in other words saying “that’s great for you” – about anything, even those that are ideas that are dangerous or stupid…
Continue reading “ChatGPT reworking from overtly Sycophant answers”AI Attempts at Ham Radio Help
There has been much research in recent months making LLMs give helpful and useful information. Unfortunately it is often wrong or inaccurate. Today I show how some simple tasks for radio amateurs are given back with incorrect information in Claude, ChatGPT and Bing AI assistant:
Continue reading “AI Attempts at Ham Radio Help”Two articles and a free Zoom weekly series on the future of AI
AI and tools like ChatGPT and Bing Assistant, Claude etc. may have changed the way we work in many industries. I just recently found that asking obscure programming questions give some surprisingly useful or halfway working responses in Microsoft Bing assistant. But will it be what some consider an AGI – a general intelligence to match human thought or ingenuity?
Continue reading “Two articles and a free Zoom weekly series on the future of AI”Will LLMs ruin SEO? It already may be happening.
In the recent article in The Atlantic, they make an interesting point – the web will likely be transformed by the junk that can be created by LLVMs and ChatGPT. This could be an increasing problem in the future, and I have seen some cases where current search engines give links to the “word salad” pages noted in the article.
Continue reading “Will LLMs ruin SEO? It already may be happening.”Recent Research Paper Notes Security Issues of ChatGPT and Other Language Models
In early March a paper was published with details of a potential vulnerability that can spread across getAI systems. For example, a mailing assistant service could be set to send out something spammy.
Continue reading “Recent Research Paper Notes Security Issues of ChatGPT and Other Language Models”ChatGPT is bad at math? Turns out, so is Microsoft’s assistant.
Recently it was noted, by Arstechnica and others, that ChatGPT doesn’t seem to be great at math questions – recent tests have found one can get wrong answers much more often than a calculator, and even apologize if you insist that it is wrong (suggesting it doesn’t know math after 2021… lol). but what about other similar assistants?
Continue reading “ChatGPT is bad at math? Turns out, so is Microsoft’s assistant.”How to build your own ChatGPT-style chat bot
In recent months, new inventions like ChatGPT have been said to be possibly the end of society, or the saving of society… but maybe this is something that is something very similar to what has been hyped before?
Continue reading “How to build your own ChatGPT-style chat bot”